- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes a student–teacher framework for semi-supervised adverse weather removal. It uses reliable and unreliable teacher predictions for contrastive learning and introduces an adaptive phase consistency loss to preserve image structure.
Critical strengths
- Retaining failed teacher predictions as negative samples is intuitive and produces clear gains in the component ablation.
- The experiments cover real-world weather removal, composite degradations, different backbones, and downstream object detection.
Critical weaknesses
- The selection of unreliable predictions is based on relative image quality scores, which may classify valid but lower-ranked restorations as failures.
- The analysis of the phase constraint mainly relies on dark-channel statistics, which do not directly demonstrate semantic preservation. The downstream detection results are reported for the complete framework, leaving the contribution of phase supervision unclear.
- The adaptive phase loss lacks comparisons with input-only, pseudo-GT-only, and fixed-weight phase constraints, leaving its advantage over simpler alternatives unclear.
Questions for authors
See Weaknesses.
2 comments
Dear Reviewer WsTC,
We sincerely thank you for the time and effort in reviewing our manuscript and providing valuable feedback. We greatly appreciate your thoughtful comments and suggestions. Should you have any further questions or concerns, we would be more than happy to provide additional clarification and engage in further discussion.
Best regards,
The authors.
Rebuttal to Reviewer WsTc
We thank the reviewer for noting that Retaining failed teacher predictions as negative samples is intuitive and for acknowledging the empirical gain of our method.
We appreciate the reviewer’s engagement with our work and offer our responses below.
Q1. The selection of unreliable predictions
We have addressed this question in the General Rebuttal. We kindly refer the reviewer to the corresponding response for further details
Q2.1. Semantic information with Fourier phase
We have addressed this question in the General Rebuttal. We kindly refer the reviewer to the corresponding response for further details.
Q2.2. Ablation study with downstream detection task
We have conducted the experiment to isolate the contribution of the proposed phase consistency loss in the downstream task and report it in the table below.
These results demonstrate that the phase consistency loss independently contributes to preserving discriminative visual information relevant to downstream object detection, beyond the improvements introduced by the unreliable database. We have revised the manuscript to explicitly highlight these controlled comparisons and clarify the individual contribution of phase-based supervision (Appendix D.1.1).
Q4. Ablation study on adaptive phase loss
To address this concern, we have conducted additional ablation experiments comparing the proposed adaptive phase consistency loss with several alternative settings, including adaptive-weight phase with input-only and pseudo-GT-only, and fixed-weight phase constraints (w=0.3 and w=0.7).
As shown in the table, our adaptive weighting strategy consistently achieves the best performance across all three weather conditions. These additional experiments validate the effectiveness of the proposed adaptive weighting mechanism over single-source and fixed-weight alternatives. We have included these results and the corresponding discussion in the revised manuscript.